Defect detection is to locate and classify the possible defects in an image, which plays a key role in the quality inspection link in the manufacturing process of industrial products. Defects in industrial products are generally very small and extremely uneven in scale, resulting in poor detection results. Therefore, we propose an efficient scale-aware network (ES-Net) to improve the effect of defect detection. By addressing the information loss of tiny targets and the mismatch between the receptive field of detection head and the scale of targets, ES-Net improves the overall defect detection effect, especially for tiny defects. Considering that existing works directly use an integrated feature to enhance features at all levels, it may cause confusion in the direction of network optimization. Therefore, we propose the aggregated feature guidance module (AFGM), which first performs efficient cascading fusion of multi-level features to filter cross-layer conflicts. Then the split and aggregation enhancement (SAE) module is designed to further optimize the integrated feature map, and the result is used to guide the shallow features. Moreover, we also introduce the multi-receptive field fusion (MFF) module to generate multi-receptive field information to supplement the shallow features after dimensionality reduction. The efficient stair pyramid (ESP) is a further improvement of feature pyramid network (FPN)-based network. In particular, we propose the dynamic scale-aware head (DSH) in shallow detection layer, which can adaptively select the best detection receptive field according to different scales of targets, thereby improving the detection performance of tiny targets. Extensive experimental results on Aliyun Tianchi fabric dataset (76.2% mAP), NEU-DET (79.1% mAP), and printed circuit board (PCB) defect dataset of Peking University (97.5% mAP) demonstrate the proposed ES-Net achieves competitive results compared to the state-of-the-art (SOTA) methods. Moreover, the high efficiency of ES-Net makes it more applicable in scenarios with high real-time requirements.

Lightweight anchor-free detectors are currently gaining more and more popularity in the field of industrial defect detection. In general, it is difficult to achieve competitive performance compared to deep anchor-based detector. Knowledge distillation is an effective way to solve this problem. In this article, we propose a novel anchor-free method based on knowledge distillation, called D-CenterNet. In our method, we employ an optimization approach using an adaptive label encoding strategy to better regress the centroid information of extreme aspect ratio (EAR) defects and improve detection accuracy. Backbone is improved for industrial defects with large aspect ratios and complex backgrounds, and strip pooling (SP) module is introduced to extract image features more efficiently. By redefining the distilled knowledge as the interrelationship between the output information, we train the student model using the pseudo-label generated by the teacher model, and then improve the model using the real label data to further enhance the performance of the student model without increasing model complexity. The experimental results on Aliyun Tianchi fabric dataset demonstrate that D-CenterNet achieves 75.5% mean average precision (mAP) and increases the mAP of the student model (60.1%, before distillation) to 63.8% (after distillation) without increasing the complexity of the model. Extensive experimental results validate the superiority of our method and demonstrate that our D-CenterNet achieves state-of-the-art (SOTA) performance in both accuracy and real-time performance.

The automatic defect detection for fabric images is an essential mission in textile industry. However, there are some inherent difficulties in the detection of fabric images, such as complexity of the background and the highly uneven scales of defects. Moreover, the trade-off between accuracy and speed should be considered in real applications. To address these problems, we propose a novel model based on YOLOv4 to detect defects in fabric images, called Feature Augmentation YOLO (FA-YOLO). In terms of network structure, FA-YOLO adds an additional detection head to improve the detection ability of small defects and builds a powerful Neck structure to enhance feature fusion. First, to reduce information loss during feature fusion, we perform the residual feature augmentation (RFA) on the features after dimensionality reduction by using 1×1 convolution. Afterward, the attention module (SimAM) is embedded into the locations with rich features to improve the adaptation ability to complex backgrounds. Adaptive spatial feature fusion (ASFF) is also applied to output of the Neck to filter inconsistencies across layers. Finally, the cross-stage partial (CSP) structure is introduced for optimization. Experimental results based on three real industrial datasets, including Tianchi fabric dataset (72.5% mAP), ZJU-Leaper fabric dataset (0.714 of average F1-score) and NEU-DET steel dataset (77.2% mAP), demonstrate the proposed FA-YOLO achieves competitive results compared to other state-of-the-art (SoTA) methods.

In this paper, we present a novel sparse Bayesian learning (SBL) framework for large-scale image recovery. We formulate variational Bayesian (VB) and generalized approximate message passing (GAMP) into the SBL model (called VGAMP-SBL) to speed up image reconstruction. GAMP can be argued a scalar estimation function described by a set of simple state evolution (SE) equations. From the SE equations, one can accurately predict the values of SBL Params, while it can obtain better reconstruction results without matrix inversion. Moreover, the interaction between data fluctuations and parameter fluctuations is negligible in VB structure, so the maximum marginal likelihood function can be easily obtained, This improves the computation efficiency of our algorithm greatly. Experimental results corroborate these claims.